moussaKam

BARThez

A french sequence to sequence pretrained model

FrugalScore

FrugalScore is an approach to learn a fixed, low cost version of any expensive NLG metric, while retaining most of its original performance

Bart_SAMSum

FInetuning BART model on samsum

OrangeSum

French Abstractive Summarization Dataset

dat_score

DATScore is a metric for NLG systems evaluation. DATScore uses multilingual MT systems to estimate the quality of machine generated documents.

arabart

An arabic pretrained seq2seq model

arabic_news_classification

A repository containing different text classification models, applied to Lebanese news articles.

Lebanese-news-word-embedding

Tool to explore Lebanese news words embedding.

dissertation-abstract

datasets

🤗 Fast, efficient, open-access datasets and evaluation metrics in PyTorch, TensorFlow, NumPy and Pandas

language-adaptive-pretraining

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

lectures-labs

Slides and Jupyter notebooks for the Deep Learning lectures at M2 Data Science Université Paris Saclay

NLP-progress

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

Spoon-Knife

This repo is for demonstration purposes only.

transfer_learning_transformers

Introduction to transfer learning in NLP using transformers.

transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

vigogne

Fine-tune French instruction-following models